Reinforcement Learning-Driven Task Offloading and Resource Allocation in Wireless IoT Networks

Mobile IoT networks face major problems in completing efficient task offloading and allocating resources effectively, as all major actions require ample energy consumption and service delays. This paper proposes a solution in the form of a reinforcement learning-based framework that is capable of dynamically optimizing these activities with the help of Group Relative Policy Optimization (GRPO). The new method outcompetes traditional heuristic-nometric methods by being able to adjust device inactivity, network activity, and available resources. Devices are structured into mobility groups and task offloading is defined as an MDP or Markov Decision Process. An ample amount of offloading strategies can be obtained by introducing declaration of tasks and corresponding computers, network throughput, and queueing delays. Additionally, GRPO aids in the allocation of computing power, network bandwidth, or storage to maximize resource allocation without breaking task deadlines and other resource limitations. Comparing the GRPO-based method to traditional methods via simulation showed increased performance and reduced service delay. The results clearly demonstrate that GRPO helps reduce service delay and consumption of energy significantly in high load with high dynamism conditions. With the inclusion of decision-making processes along with constraint-tolerance and reinforcement learning, this research aids in IoT frameworks that require low energy output with less delay. The recommended method helps build a strong base for efficient task delegation alongside increased performance and scalability, which subsequently enhances AI edge computing and smart management of IoT systems.